Automatic navigation for mobile robot to avoid obstacles in unknown environment based on Q-learning algorithm
Keywords:
Artificial intelligence, Mobile robot control, Q-learning algorithm, Reinforcement learningAbstract
This article presents a method to build an intelligent automatic navigation system for multi-directional mobile robots in an unknown flat environment. The studies using programming tools are the operating system for mobile robots (Robot Operating System ROS). From updates on maps, operating environment, robot control position, and obstacles (Simultaneous Localization and Mapping (SLAM)) to calculating the trajectory of the robot in the navigation system automatically avoids the obstacles. The navigation system calculates the global and local orbit for the robot based on the application of Qlearning algorithm. The results of simulation studies in the Gazebo environment and especially the experimental run on the real Turtlebot mobile robot have shown the practical effectiveness of automatic navigation for this mobile robot.
References
A. Folkers, M. Rick, and C. Buskens, “Controlling an autonomous vehicle with deep reinforcement learning,” IEEE Intell. Veh. Symp. Proc., vol. 2019-June, (2019), pp. 2025–2031.
Cuong Nguyen Manh, Tien Ngo Manh, Dung Pham Tien, Van Nguyen Thi Thanh, Manh Tran Van, Duyen Ha Thi Thanh and Duy Nguyen Duc “Autonomous Navigation for Omnidirectional Robot Based on Deep Reinforcement Learning,” IJMERR, Vol. 9, No. 8, August (2020), pp: 1134-1139.
Do Quang Hiep, Ngo Manh Tien, Nguyen Manh Cuong, Pham Tien Dung, Tran Van Manh, Nguyen Tien Kiem, Nguyen Duc Duy, “An Approach to Design Navigation System for Omnidirectional Mobile Robot Based on ROS”, IJMERR, Volume 11; Issue 9; (2020), pp: 1502-1508.
Roan Van Hoa, Tran Duc Chuyen, Nguyen Tung Lam, Nguyen Duc Dien, Tran Ngoc Son, Vu Thi To Linh, “Reinforcement Learning based Method for Autonomous Navigation of Mobile Robots in Unknown Environments”, Proceedings of the 2020 International Conference on Advanced Mechatronic Systems, Hanoi, Vietnam, December 10 - 13, (2020), pp. 266-269.
Hado van Hasselt, “Double Q – learning” Advances in neural information processing systems, (2010) pp. 1-9.
L. Xin, Q. Wang, J. She, and Y. Li, “Robust adaptive tracking control of wheeled mobile robot,” Robotics and Autonomous Systems, vol. 78, (2016), pp. 36–48.
Shota Ohnishi, Eiji Uchibe, Yotaro Yamaguchi, Kosuke Nakanishi, Yuji Yasui and Shin Ishii, “Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning”, Vol 13, Publishing by Frontiers in Neurorobotics Journal, December (2019), pp 7-12.
Andrea Bacciotti, "Stability and Control of Linear Systems“, Publishing Ltd; Springer Nature Switzerland AG, (2019).
Charu C. Aggarwal, “Neural Networks and Deep Learning”, Springer International Publishing AG, part of Springer Nature, 2018.
Nguyen Thanh Tuan, “Base Deep learning”, The Legrand Orange Book. Version 2, last update, August (2020).
Tran Hoai Linh, “Neural network and its application in signal processing”, Hanoi Polytechnic Publishing House, (2015).
Nils J. Nilsson, “The quest for artificial interlligence a history of ideas and achievements”, Web Version Print version published by Cambridge University Press, Publishing September 13, (2010).
Vu Thi Thuy Nga, Ong Xuan Loc, Trinh Hai Nam, “Enhanced learning in automatic control with Matlab simulink”, Hanoi Polytechnic Publishing House, (2020).
V. Matt and N. Aran, “Deep reinforcement learning approach to autonomous driving,” ed: arXiv, (2017).
https://www.mathworks.com/help/reinfocerment-learning/ug/ddpg - Agent. html, (2020).
